© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244304
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     administers
    0.38
     estruct
    0.38
     struct
    0.37
     structural
    0.37
     &\
    0.36
     strukt
    0.35
     vista
    0.35
    ጊ
    0.34
     structuring
    0.34
    oj
    0.34
    POSITIVE LOGITS
     ट्रेस
    0.39
    DUT
    0.39
     tham
    0.37
     वन्य
    0.34
    SECUR
    0.34
     शेयरों
    0.34
     då
    0.34
    город
    0.34
    erais
    0.33
     avere
    0.33
    Activations Density 0.000%

    No Known Activations